Create a draft reply

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the annotations (readOnlyHint=false, destructiveHint=false, idempotentHint=false, openWorldHint=true), the description discloses the important behavioral facts: the reply lands in the same thread, the recipient is derived from Reply-To, and nothing is transmitted externally until a human sends it. It does not address whether repeated calls create duplicate drafts, which is relevant given idempotentHint=false.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two tight sentences with no waste; the operation and its key constraint (nothing is sent) are front-loaded, and the parenthetical Reply-To detail is compactly integrated.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a two-parameter tool with full schema coverage and annotations, the description covers purpose, thread/recipient behavior, and the no-send guarantee. The one gap is the return value: with no output schema, an agent cannot tell whether it receives a draft id or thread id from the call.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds meaningful semantics: the body is plain-text only, and message_id implicitly determines both the thread and the recipient (no separate recipient parameter exists). That explains a non-obvious consequence of a parameter beyond its schema text.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Save a plain-text reply ... as a Gmail draft') plus the scope details (same thread, addressed to original sender/Reply-To). This is clearly a draft-creation write operation, unmistakable from the read-only siblings search_emails, get_email, and get_thread.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The phrase 'Nothing is sent: a person reviews and sends the draft from Gmail' establishes the context in which this tool is appropriate (human-in-the-loop drafting) and implicitly rules out use as an auto-send mechanism. It does not name an alternative send tool or state exclusions explicitly, so it stops short of full routing guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.